Network Intrusion Detection Systems (NIDS) are designed to safeguard the security needs of enterprise networks against cyber-attacks. However, NIDS networks suffer from several limitations, such as generating a high volume of low-quality alerts. Moreover, 99% of the alerts produced by NIDSs are false positives. As well, the prediction of future actions of an attacker is one of the most important goals here. The study has reviewed the state-of-the-art cyber-attack prediction based on NIDS Intrusion Alert, its models, and limitations. The taxonomy of intrusion alert correlation (AC) is introduced, which includes similarity-based, statistical-based, knowledge-based, and hybrid-based approaches. Moreover, the classification of alert correlation components was also introduced. Alert Correlation Datasets and future research directions are highlighted. The AC receives raw alerts to identify the association between different alerts, linking each alert to its related contextual information and predicting a forthcoming alert/attack. It provides a timely, concise, and high-level view of the network security situation. This review can serve as a benchmark for researchers and industries for Network Intrusion Detection Systems’ future progress and development.

No abstract

No abstract

The Internet of Things (IoT) has grown into various enterprise. While the IoT ecosystem's extensive and open environment has many advantages, it can also be a target for a range of growing cyber risks and assaults. The bene ts of device integration into a smart ecosystem are enhanced by the IoT's diversity, but the IoT's diverse nature makes establishing a single security solution di cult. However, softwarede ned networks' (SDNs) centralized intelligence and programmability, it's now possible to put together a single, effective security solution to combat cyber threats and attacks. This study proposes a DL-driven SDN-enabled IoT framework that practice a Deep Neural Network-Long Short-Term Memory (LSTM) classi er to quickly and e ciently detect sophisticated multisector malware botnets. The proposed mechanism was rigorously tested utilizing the most recent state-of-the-art dataset, CICIDS2017, as well as traditional performance evaluation metrics. Furthermore, the proposed technique is compared to current industry norms (i.e., DL algorithms). Extensive testing shows that the proposed method surpasses the competition in terms of detection accuracy while requiring just a minimal compromise in terms of computational cost.

Diagnostic image volume and complexity in healthcare system increases in rapid pace where available human proficiency may not sufficient for interpreting this much capacity of image data. Machine learning approaches exposed excessive potential to knob huge amount of two-dimensional annotated images of common illnesses from large databases. Deep learning imitates human for extracting knowledge from dataset and favourable to data scientists for accumulating, analysing, interpreting and predictive modelling. In this paper organ inflammation disease is addressed with Deep Learning Neural Network (DLNN) based classification scheme is incorporated to diagnose or prognoses the patient from severity, based on their historical database. In pandemic environment collecting histopathology tissue score is time consuming process due to a smaller number of physician availability, by implementing proposed DLNN algorithm suits for collecting organ inflammation score and categorizing its brutality by classification of pancreatitis, duodenum and appendix. In order to achieve accuracy and sensitivity of various stages soreness DLNN based algorithm is developed and it supports by classifying the datasets.